Google Text to Speech with Audio Tags
Gemini 3.1 Flash TTS generates expressive speech with audio tags that control pacing, tone, pauses and emphasis, alongside standard Google voices.
- 2 variants
- Price
- See price
- Speed
- ~5s
- Best for
- Voice · Text to Voice
- Price
- See price
- Speed
- ~10s
- Best for
- Voice · Text to Voice
More from Google.
A family groups the versions of one model line. Open one to compare its variants side by side.
Working with Google Text to Speech.
Two speech models sit in this family. Gemini 3.1 Flash TTS is the expressive one: audio tags inside the text control pacing, tone, pauses and emphasis, so delivery is directed rather than left to the model. Google Text to Speech is the straightforward converter — pick a voice, submit text, get audio.
When to choose Google Text to Speech
Choose this family when the delivery of the line matters and you want to direct it inline. Kling Voice is for custom voices bound to Kling video; ByteDance Seed Audio is the option with sample-rate, speed and pitch controls.
Choosing between the variants
Gemini 3.1 Flash TTS is the one to use when a script needs emphasis, pauses or a change of tone mid-sentence. Google Text to Speech is simpler and faster to wire up when plain narration is all you need.
Questions about Google Text to Speech
The short answers. For anything specific to your setup, talk to our team.
Talk to an engineerPlan for your expected volume.Inline markers in the submitted text that control pacing, tone, pauses and emphasis, so you direct the read instead of re-rolling the generation.
Yes. Google Text to Speech exposes a voice selection, so the same script can be rendered by different speakers.
Gemini 3.1 Flash TTS, because pacing and pause control keep a long read from sounding flat across paragraphs.